INDEX

Explanations

code function calls and definitions

This neuron activates on identifiers used in dotted code expressions (object or module names in “name.method” or “Module.Property” access).

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

嘞

-1.80

 jepang

-1.77

呦

-1.75

 that

-1.67

ffilm

-1.63

哟

-1.62

啊啊

-1.60

Publié

-1.57

 deaktiviert

-1.55

對於

-1.45

POSITIVE LOGITS

and

2.27

or

2.11

或

1.60

 primit

1.55

1.54

푆

1.41

 tandis

1.41

軚

1.37

rairie

1.37

to

1.37

Activations Density 0.060%